Govgrant.ca
Production RAG platform · lead engineer · 2025-2026
A Canadian grant-discovery platform that matches businesses with relevant funding programs using RAG-based recommendations.
2,000+ users and 300+ grants refreshed daily
the problem
Canadian businesses had to search fragmented government sources, interpret eligibility criteria, and repeatedly check whether programs were still open. The product needed to make discovery faster without presenting stale or irrelevant opportunities.
technical context
- Matching quality depended on combining business context with current grant data and useful eligibility information.
- The ingestion process had to refresh hundreds of grants daily while retaining enough structure for retrieval and administration.
- The AI workflow ran inside a subscription product, so authentication, billing, admin controls, and recommendation delivery had to work together.
my role and technical scope
As Lead Engineer, I built the grant-matching experience and core SaaS platform, including RAG recommendations, the automated grant pipeline, authentication, subscriptions, billing, and administration.
architecture and engineering decisions
- Grounded RAG recommendations in structured grant information and current source content.
- Automated grant ingestion and refreshes rather than relying on a manually maintained catalogue.
- Included freshness, eligibility context, and admin tooling in the production workflow.
- Integrated the matching system with authentication, subscriptions, billing, and the rest of the SaaS platform.
what shipped
- RAG-based matching and recommendation workflows
- Automated ingestion processing more than 300 grants per day
- Authentication, billing, subscriptions, and administration
- Production infrastructure supporting more than 2,000 users
outcomes
- Served more than 2,000 users across Canada
- Kept the grant catalogue current through a daily automated pipeline
- Connected AI recommendations to a usable, monetizable SaaS workflow
engineering priorities
- Grant-ingestion success rate and source freshness
- Retrieval quality, recommendation latency, and groundedness
- Subscription and billing workflow reliability
- Admin error visibility and recovery time
what I learned
RAG quality depends on the whole data path: source freshness, structured records, retrieval, and operational tools all affect the recommendations users see.
engineering strengths demonstrated
- RAG implementation in production
- Automated data ingestion
- Full-stack SaaS engineering
- Technical ownership at scale